def test_distribute_fpn_proposals(self):
rois_np = np.random.rand(10, 4).astype('float32')
rois_num_np = np.array([4, 6]).astype('int32')
with self.static_graph():
rois = paddle.static.data(name='rois',
shape=[10, 4],
dtype='float32')
rois_num = paddle.static.data(name='rois_num',
shape=[None],
dtype='int32')
multi_rois, restore_ind, rois_num_per_level = ops.distribute_fpn_proposals(
fpn_rois=rois,
min_level=2,
max_level=5,
refer_level=4,
refer_scale=224,
rois_num=rois_num)
fetch_list = multi_rois + [restore_ind] + rois_num_per_level
output_stat = self.get_static_graph_result(feed={
'rois': rois_np,
'rois_num': rois_num_np
},
fetch_list=fetch_list,
with_lod=True)
output_stat_np = []
for output in output_stat:
output_np = np.array(output)
if len(output_np) > 0:
output_stat_np.append(output_np)
with self.dynamic_graph():
rois_dy = base.to_variable(rois_np)
rois_num_dy = base.to_variable(rois_num_np)
multi_rois_dy, restore_ind_dy, rois_num_per_level_dy = ops.distribute_fpn_proposals(
fpn_rois=rois_dy,
min_level=2,
max_level=5,
refer_level=4,
refer_scale=224,
rois_num=rois_num_dy)
output_dy = multi_rois_dy + [restore_ind_dy
] + rois_num_per_level_dy
output_dy_np = []
for output in output_dy:
output_np = output.numpy()
if len(output_np) > 0:
output_dy_np.append(output_np)
for res_stat, res_dy in zip(output_stat_np, output_dy_np):
self.assertTrue(np.array_equal(res_stat, res_dy))
def __call__(self, feats, rois, spatial_scale):
roi, rois_num = rois
cur_l = 0
if self.start_level == self.end_level:
rois_feat = ops.roi_align(feats[self.start_level],
roi,
self.resolution,
spatial_scale,
rois_num=rois_num)
return rois_feat
offset = 2
k_min = self.start_level + offset
k_max = self.end_level + offset
rois_dist, restore_index, rois_num_dist = ops.distribute_fpn_proposals(
roi,
k_min,
k_max,
self.canconical_level,
self.canonical_size,
rois_num=rois_num)
rois_feat_list = []
for lvl in range(self.start_level, self.end_level + 1):
roi_feat = ops.roi_align(feats[lvl],
rois_dist[lvl],
self.resolution,
spatial_scale[lvl],
sampling_ratio=self.sampling_ratio,
rois_num=rois_num_dist[lvl])
rois_feat_list.append(roi_feat)
rois_feat_shuffle = paddle.concat(rois_feat_list)
rois_feat = paddle.gather(rois_feat_shuffle, restore_index)
return rois_feat
def __call__(self, feats, roi, rois_num):
roi = paddle.concat(roi) if len(roi) > 1 else roi[0]
if len(feats) == 1:
rois_feat = ops.roi_align(feats[self.start_level],
roi,
self.resolution,
self.spatial_scale[0],
rois_num=rois_num,
aligned=self.aligned)
else:
offset = 2
k_min = self.start_level + offset
k_max = self.end_level + offset
rois_dist, restore_index, rois_num_dist = ops.distribute_fpn_proposals(
roi,
k_min,
k_max,
self.canconical_level,
self.canonical_size,
rois_num=rois_num)
rois_feat_list = []
for lvl in range(self.start_level, self.end_level + 1):
roi_feat = ops.roi_align(feats[lvl],
rois_dist[lvl],
self.resolution,
self.spatial_scale[lvl],
sampling_ratio=self.sampling_ratio,
rois_num=rois_num_dist[lvl],
aligned=self.aligned)
if roi_feat.shape[0] > 0:
rois_feat_list.append(roi_feat)
rois_feat_shuffle = paddle.concat(rois_feat_list)
rois_feat = paddle.gather(rois_feat_shuffle, restore_index)
return rois_feat